scispace - formally typeset
K

Klára Vicsi

Researcher at Budapest University of Technology and Economics

Publications -  73
Citations -  808

Klára Vicsi is an academic researcher from Budapest University of Technology and Economics. The author has contributed to research in topics: Speech processing & Acoustic model. The author has an hindex of 14, co-authored 70 publications receiving 698 citations.

Papers
More filters
Journal ArticleDOI

Using prosody to improve automatic speech recognition

TL;DR: The HMM framework is used to model speech prosody, and to perform initial syntactic and/or semantic level processing of the input speech in parallel to standard speech recognition, and the N-best rescoring based on syntactic level word-stress unit alignment was shown to augment the number of correctly recognized words.
Proceedings ArticleDOI

BABEL: an Eastern European multi-language database

TL;DR: The project is producing a multi-language database of five of the most widely-differing Eastern European languages (Bulgarian, Estonian, Hungarian, Romanian and Polish).

Speech Emotion Perception by Human and Machine.

TL;DR: An automatic emotion recognition system was developed and recordings of 3 Hungarian sentences with 8 basic emotions pronounced by nonprofessional speakers showed similar recognition results as an earlier perception test obtained with professional actors/actresses.
Journal ArticleDOI

A Multimedia, Multilingual Teaching and Training System for Children with Speech Disorders

TL;DR: The article presents the measuring methods, the used distance score calculations of the visualized speech spectra, and problems in the evaluation of the new multimedia tool.
Book ChapterDOI

Speech Emotion Perception by Human and Machine

TL;DR: In this paper, an automatic emotion recognition system was developed by using statistical methods (HMM) to train different emotional models and optimization of the recognition was done by changing the acoustic preprocessing parameters and the number of states of the Markov models.